WO2024023930A1 - 変換装置、変換方法、及びプログラム - Google Patents

変換装置、変換方法、及びプログラム Download PDF

Info

Publication number
WO2024023930A1
WO2024023930A1 PCT/JP2022/028792 JP2022028792W WO2024023930A1 WO 2024023930 A1 WO2024023930 A1 WO 2024023930A1 JP 2022028792 W JP2022028792 W JP 2022028792W WO 2024023930 A1 WO2024023930 A1 WO 2024023930A1
Authority
WO
WIPO (PCT)
Prior art keywords
unit
information
conversion
person
character
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2022/028792
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
陽子 石井
桃子 中谷
晴美 齋藤
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NTT Inc
Original Assignee
Nippon Telegraph and Telephone Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nippon Telegraph and Telephone Corp filed Critical Nippon Telegraph and Telephone Corp
Priority to JP2024536596A priority Critical patent/JPWO2024023930A1/ja
Priority to PCT/JP2022/028792 priority patent/WO2024023930A1/ja
Priority to US18/994,282 priority patent/US20260030447A1/en
Publication of WO2024023930A1 publication Critical patent/WO2024023930A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/274—Converting codes to words; Guess-ahead of partial word inputs
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue

Definitions

  • the present invention relates to technology for displaying character information.
  • Non-Patent Document 1 discloses a speech recognition system that automatically converts the content of a person's utterance into text in real time.
  • the general speech recognition system disclosed in Non-Patent Document 1 and the like since the utterance content is only displayed as text information, it is difficult to read the relationship between a plurality of utterance content from the text information.
  • the present invention has been made in view of the above points, and provides a technology that makes it possible to display textual information so that the relationships between a plurality of utterances can be easily read from the textual information.
  • the purpose is to
  • a character conversion unit that converts input information into character information
  • a selection unit that selects character information to be displayed from one or more character information obtained by the character conversion unit
  • a conversion device comprising: a coordinate conversion section that converts the character information selected by the selection section into coordinates corresponding to a display position thereof.
  • a technology that makes it possible to display textual information so that the relationships between a plurality of utterances can be easily read from the textual information.
  • FIG. 1 is a diagram showing an example of the overall configuration of a visualization system. It is a flowchart for explaining the operation of the conversion device.
  • FIG. 3 is a diagram for explaining coordinates on a display screen. It is a figure showing an example of a display.
  • FIG. 7 is a diagram illustrating a conversion device of Modification 1.
  • FIG. 7 is a diagram illustrating a conversion device of Modification 1. It is a diagram showing an example of the hardware configuration of the device.
  • the technology according to the present invention is not limited to this assumption and can be applied to a wide range of general dialogue situations.
  • the technology according to the present invention in a conversation without a facilitator, the contents of an arbitrary person's utterances can be displayed in a manner that makes it easy to understand the relevance of the contents of the utterances.
  • text is used as an example of the text information to be displayed, but the text information to be displayed is not limited to "text".
  • the character information to be displayed may be a sentence, a word, a symbol, or other information.
  • the facilitator simply inputs the utterance content (sentences) into the conversion device 100 sequentially using voice input or a keyboard, and the conversion device 100 adjusts the sentences to match the similarity in meaning (In other words, the two-dimensional coordinates at which the summarized sentences should be placed are automatically calculated (so that the relationships between sentences can be easily understood).
  • the conversion device 100 is configured to It is possible to judge the reactions of users and display sentences that have a characteristic reaction preferentially. In other words, it can be said that the sentences with characteristic reactions represent the content of the discussion at the time, and therefore the conversion device 100 can extract the content of the discussion at the time in an easy-to-understand manner.
  • FIG. 1 shows an example of the configuration of a visualization system according to this embodiment.
  • the visualization system of this embodiment is used in situations where two or more people are having a conversation.
  • the example shown in FIG. 1 shows a situation in which three people 1 to 3 are participating in a dialogue. Note that the configuration shown in FIG. 1 will be referred to as a "basic example.”
  • One of the three people is a facilitator whose role is to facilitate dialogue among participants.
  • the visualization system shown in FIG. 1 includes a conversion device 100, a video camera 10, microphones 20, 30, 50, and sensing devices 40, 60.
  • the conversion device 100 is, for example, a computer such as a PC (personal computer).
  • a keyboard 180 and a display unit 190 are connected to a conversion device 100.
  • the display unit 190 may be a functional unit that constitutes the conversion device 100.
  • keyboard 180, video camera 10, microphones 20, 30, 50, and sensing devices 40, 60 are all examples of input units that input information to the conversion device 10. Any of the input units may be a functional unit that constitutes the conversion device 100.
  • the conversion device 100 includes a character conversion section 110, a selection section 120, an initial value setting section 130, another person's reaction judgment section 140, a theme content transmission section 150, a coordinate conversion section 160, and a storage section 170.
  • the initial value setting unit 130 sets in advance a period T (a period of 1 second or more), a numerical value a (an integer of 1 or more), and the size of the area in which the utterance content is displayed on the display unit 170. (displayX, displayY), and retains the received information.
  • displayX, displayY For example, a keyboard 180 is used for input here.
  • the units of displayX and displayY are pixels.
  • the character conversion unit 110 acquires a sentence by converting the voice input from the microphone 20 into character information. Furthermore, the character conversion unit 110 converts information input from the keyboard 180 (specifically, a string of signals such as codes) into text.
  • the character conversion unit 110 performs a summary process on the text obtained through conversion to obtain a summary of the text (summarized text). Any conventional technique for text summarization can be used. As an example, text can be summarized using the technique disclosed in Japanese Patent Application Publication No. 2011-28638.
  • the character conversion unit 110 counts the number of characters in a sentence, performs summarization so that the number of characters is below a certain threshold, and selects the summarized text (this may be referred to as a "summary"). 120.
  • the other person's reaction determining unit 140 is a functional unit that determines the reaction of a person other than the person making the utterance.
  • the person making the utterance to be summarized is the facilitator (person 1), and the other person's reaction judgment unit 140 judges the reaction of persons other than the facilitator to the facilitator's utterance. do.
  • the other person's reaction judgment unit 140 includes three types of devices: a video camera that photographs the people who are having a conversation, a microphone that collects the utterances of the people who are having the conversation, and a sensing device that senses the people who are having the conversation. At least one type of device among the devices is connected. For example, as many microphones and sensing devices as there are people participating in the dialogue (excluding the facilitator) are prepared.
  • a video camera 10 is provided, as well as a microphone 30 and sensing device 40 for person 2, and a microphone 50 and sensing device 60 for person 3.
  • the conversion device 100, video camera 10, microphones 20, 30, 50, and sensing devices 40, 60 are all synchronized in time.
  • the operation when a video camera is provided, the operation when a microphone is provided, and the operation when a sensing device is provided will be explained.
  • the microphones 20, 30, and 50 may be of any type; for example, a headset microphone, a lavalier microphone, a gooseneck microphone, etc. can be used.
  • the sensing devices 40 and 60 may be of any type, but for example, the sensing devices may include a built-in at least one of a gyro sensor, a heart rate measuring device, and an electroencephalogram sensor. can be used.
  • the image acquired by the video camera is input to the other person's reaction judgment unit 140, and the other person's reaction judgment unit 140 uses the image to determine the individual person's behavior in real time by using, for example, the API of a posture estimation service (e.g., OpenPose). Obtain the position information of the skeleton.
  • a posture estimation service e.g., OpenPose
  • the other person's reaction determination unit 140 detects the person's movements such as nodding, shaking the head, leaning forward, etc. from time-series changes in the position information of the person's skeleton. Detection of a person's motion by the other person's reaction determination unit 140 may be performed based on the positional relationship between certain skeletons, or may be performed based on the time-series changing movement of one or more skeletons.
  • a plurality of motions are set for the other person's reaction determination unit 140 as motions to be detected. Also, a certain numerical value is set for each operation.
  • the other person's reaction determination unit 140 detects a certain action for a certain person, it obtains the numerical value set for that action as the weight ⁇ .
  • the other person's reaction determining unit 140 sends the weight ⁇ obtained by detecting the movement to the selection unit 120 together with time information t when the movement occurred.
  • the respective weights for the multiple movements may be sent to the selection unit 120, or based on predetermined rules, one of the multiple movements may be detected. It may be possible to select any one action and send the weight of the selected action to the selection unit 120, or it may be possible to send a sum of the respective weights for the plurality of actions to the selection unit 120.
  • ⁇ Microphone operations> The audio of each conversation participant's utterances is input to the other person's reaction determination unit 140 in real time by a microphone provided to each conversation participant.
  • the other person's reaction determination unit 140 performs the following processing on each person's voice.
  • the other person's reaction determination unit 140 uses, for example, an emotion understanding engine of existing technology to associate the acquired utterance audio with a numerical value representing the intensity of emotion.
  • a certain threshold value and a numerical value corresponding to a case where the numerical value representing the intensity of emotion exceeds (or falls below the threshold value) the threshold value are preset in the other person reaction determination unit 140.
  • the other person's reaction determination unit 140 sets the numerical value for the intensity of the emotion detected based on the voice input from the microphone as a weight ⁇ .
  • the other person's reaction determination unit 140 sends the weight ⁇ obtained by detecting the intensity of emotion based on the voice to the selection unit 120 together with time information t when the utterance corresponding to the weight ⁇ occurred.
  • the other person reaction determination unit 140 performs the following process to determine the weight ⁇ may be obtained and sent.
  • One or more predetermined phrases such as "I see” and “Huh” are set in advance in the other person's reaction judgment unit 140. Further, a numerical value is set for each phrase, and the numerical value is set as a weight ⁇ . That is, when the other person's reaction determining unit 140 detects a preset phrase from the uttered voice, it sends the numerical value corresponding to the uttered voice as the weight ⁇ to the selection unit 120 together with the time information t.
  • the other person's reaction determination unit 140 may perform either weight calculation based on the numerical value of the emotional intensity or weight calculation based on the phrase, or may perform both.
  • the respective weights ⁇ may be sent to the selection unit 120 together with the time information t, or one of the weights may be selected based on a predetermined rule and sent to the selection unit 120 together with the time information t.
  • the sum of both weights may be used as the weight ⁇ and sent to the selection unit 120 together with the time information t.
  • Sensing information (output data from the sensing device) for each conversation participant is input to the other person's reaction determination unit 140 in real time by the sensing device provided for each conversation participant.
  • the other person's reaction determination unit 140 performs the following processing on the sensing information of each person.
  • One sensing device may be provided for each person, or multiple sensing devices of different types may be provided.
  • the other person's reaction determination unit 140 detects a preset characteristic from the output data of each sensing device.
  • a plurality of characteristics and a numerical value for each characteristic are preset in the other person's reaction determination section 140.
  • the other person's reaction determination unit 140 obtains a numerical value corresponding to the detected feature as a weight ⁇ .
  • the other person's reaction determination unit 140 sends the weight ⁇ acquired based on the detection of a certain feature to the selection unit 120 together with time information t when the feature occurred.
  • the above-mentioned “feature” may be of any kind, but for example, the detection of a state in which the value of sensing information exceeds (or falls below) a preset threshold value may be detected. Alternatively, the detection of a predetermined change from a time-series change in sensing data may be taken as the detection of a feature.
  • the respective weights for the plurality of features may be sent to the selection unit 120, or one of the plurality of features may be selected based on a predetermined rule.
  • a feature may be selected and the weight of the selected feature may be sent to the selection unit 120, or a value obtained by adding up the weights of the plurality of features may be sent to the selection unit 120.
  • ⁇ S104 Sending information regarding the topic>
  • the theme content transmitting unit 150 transmits the sentence of the theme registered in advance in the storage unit 170 and the time s for the facilitator to speak about the theme to the coordinate conversion unit 160 and the selection unit 120 .
  • the theme content transmitting unit 150 transmits the text of the added theme and the time s for speaking about the theme to the coordinate conversion unit 160 and the selection unit 120.
  • “theme” may be replaced with “topic”, “theme”, “topic”, etc.
  • the theme and time s are stored in the storage unit 170, they are stored together with a number that identifies the theme. Further, regarding the theme transmitted to the selection unit 120, the information transmitted may be the text of the theme and a number for identifying the theme, or may be only a number for identifying the theme.
  • the text of the theme and the time s for the facilitator to speak about the theme may be sent only to the coordinate conversion unit 160 and not to the selection unit 120.
  • the selection unit 120 receives the text summary from the character conversion unit 110.
  • the summary is a summary of the sentence input as voice or text by the facilitator.
  • the start time and end time of the utterance corresponding to the summary are set in the summary. Note that the meaning of "utterance” includes not only vocalization but also input using a keyboard.
  • the selection unit 120 sequentially receives the summaries from the character conversion unit 110. That is, during a certain period of time, the selection unit 120 receives a plurality of summaries from the character conversion unit 110. However, during a certain period of time, the selection unit 120 may receive only one summary from the character conversion unit 110.
  • the selection unit 120 When the selection unit 120 receives the weight ⁇ and time information t from the other person reaction determination unit 140, if there is a summary corresponding to the time including the received time information t, the selection unit 120 adds the weight ⁇ received together with the time information t to the summary. Map the values of . For example, if the start time to end time of the summary is T to T+10, and the time information t received together with the weight ⁇ is T+5, the weight ⁇ is associated with the summary.
  • a period "start time - end time + nt", which is obtained by adding a time nt (described later) to the end time of the period "start time - end time” of the summary, may be used for the determination.
  • the selection unit 120 receives the weight ⁇ and time information t from the other person reaction determination unit 120, if the received time information t is included in “opening time to end time + nt”, the selection unit 120 adds the time to the summary. The value of the weight ⁇ received together with the information t is associated.
  • the selection unit 120 sets the sum of all the weights ⁇ as the weight of the summary.
  • the selection unit 120 receives information from the other person's reaction determination unit 140 regarding the time after the end time of the summary only for a predetermined time nt from the end time of the summary, and selects information received at a time after that time. will be discarded.
  • the time nt is managed by the selection section 12, and even if the time information t sent from the other person's reaction judgment section 140 is actually within "opening time - end time + nt", when it is received, If "end time + nt" has elapsed, the received information is discarded.
  • processing is only an example.
  • the selection unit 12 sets the weight of the summary to 0.
  • the selection unit 120 receives the period T and the value of the numerical value a from the initial value setting unit 130, and selects a summary summarized during the period T as a summary to be displayed as a candidate based on a predetermined rule. Select. Examples of selection rules are as follows. Note that the summary summarized during the period T is, for example, a summary in which the period T includes "start time to end time". Note that if there are no a summaries summarized during period T, all summaries summarized during period T may be selected.
  • the selection unit 120 selects summary 3 (start time t+1, weight 6), summary 1 (start time t, weight 5), and summary 2 (start time t-1, weight 4) based on the weights.
  • summary 1 start time t, weight 5
  • summary 2 start time t-1, weight 4
  • summary 3 start time t+1, weight 4
  • summary 4 start time t-2, weight 4
  • the selection unit 120 sets topic information indicating which topic was discussed for each selected summary. For example, based on the theme and the time s received from the theme content transmitting unit 150, the selection unit 120 sets the theme in the summary summarized within the time s.
  • the theme information set in the summary is, for example, a number by which the theme can be identified.
  • time information for example, information that time s is the time from time a to time b
  • time s is added to "time s". This can be achieved by including
  • the facilitator when the facilitator is talking about a topic that has been registered in the storage unit 170, as the conversation progresses, the facilitator selects the topic that is currently being talked about using the keyboard 180, etc. When the topic changes, the facilitator may also reselect the topic. The number of the theme is set in the summary of the content uttered while the theme is selected by the facilitator (until the theme is selected again).
  • the facilitator or other person inputs the theme manually or by voice input using an input device such as a keyboard or a microphone, and registers it in the storage unit 170.
  • the storage unit 170 when a new theme is registered, a number is also assigned to the new theme, and information such as the number is returned from the theme content transmission unit 150 to the selection unit 120.
  • the selection unit 120 sets the number of the theme to the summary of the utterance of the theme.
  • the summary selected by the selection unit 150 is sent to the coordinate conversion unit 160 along with the theme number corresponding to the summary.
  • the coordinate transformation unit 160 transforms each summary into high-dimensional coordinates (high-dimensional vectors). Any method may be used to convert the text of the summary into high-dimensional coordinates; for example, doc2vec or fast2text can be used.
  • the high-dimensional coordinates obtained here are also called distributed representations and indicate the features of the summary.
  • Both doc2vec and fast2text are examples of conversion models that extract features from text information such as sentences.
  • the number of dimensions of this high-dimensional coordinate is, for example, 200. Any numerical value can be specified for the number of dimensions.
  • the coordinate conversion unit 160 performs principal component analysis on the coordinates converted from the summary to compress the dimensions and obtain two-dimensional coordinates (aX, aY). These two-dimensional coordinates (aX, aY) also indicate the feature amount of the summary.
  • the coordinate conversion unit 160 sends the number of the theme received along with the summary to the storage unit 170, and checks whether coordinates are registered for the theme. If the coordinates are registered in the storage unit 170, the storage unit stores the center coordinates (titleX', titleY') of the rectangular area corresponding to the theme and (summaryX, summaryY) representing the size of the area. Obtained from 170.
  • the coordinate conversion unit 160 executes the following coordinate conversion process.
  • the coordinate conversion unit 160 receives the theme sentence corresponding to the inquired theme number and the time s for speaking about the theme from the storage unit 170, and performs the following processing.
  • the coordinate conversion unit 160 converts the subject sentence into high-dimensional coordinates using, for example, doc2vec or fast2text, in the same manner as the coordinate conversion for the summary, and performs principal component analysis on the converted coordinates. Dimensionally compress and obtain two-dimensional coordinates (titleX, titleY).
  • the coordinate conversion unit 160 receives from the initial value setting unit 130 the sizes displayX and displayY of the rectangular area in which the conversation content (utterance content) is displayed on the display unit 190.
  • the units of displayX and displayY are pixels.
  • the coordinate conversion unit 160 projectively transforms the coordinates of the theme (titleX, titleY) to the size of the area where the dialogue content is displayed, and obtains the coordinates (titleX', titleY').
  • the coordinate conversion unit 160 calculates the topic speaking time sn for all the topics scheduled to be talked about this time (s1 if the topic number is 1, s1 if the topic number is n, etc.) , the period T and the numerical value a are obtained from the storage unit 170. Note that here, it is assumed that the period T and the numerical value a are held in the storage unit 170.
  • the coordinate conversion unit 160 obtains the values of (titleX', titleY') and (summaryX, summaryY) for each theme. Subsequently, the coordinate transformation unit 160 performs the following processing for each theme and each summary.
  • the coordinate transformation unit 160 projectively transforms the two-dimensional coordinates (aX, aY) of the summary into summaryX, summaryY to obtain (aX', aY').
  • the coordinate transformation unit 160 transforms (aX', aY') using the following formula so that (titleX'-summaryX/2, titleY'-summaryY/2) is the origin (aX Find ⁇ ⁇ , aY ⁇ ⁇ ).
  • the coordinate conversion unit 160 sends each piece of coordinate information including the determined (aX'', aY'') and information such as a summary to be displayed to the display unit 190.
  • the display unit 190 displays the text of the summary at the position (aX'', aY'') for each topic and each summary.
  • the display unit 190 also displays the title at (titleX', titleY') for each title. Please note that if the topic is already displayed, it will not be overwritten.
  • Figure 3 shows an image of each coordinate.
  • summary display areas for two themes, summaryX1 ⁇ summaryY1 and summaryX2 ⁇ summaryY2 are shown in the displayX ⁇ displayY area.
  • the display position of theme 1 (titleX1 ⁇ , titleY1 ⁇ ) and the display position of theme 2 (titleX2 ⁇ , titleY2 ⁇ ) are shown.
  • the display position of summary 1 (aX1 ⁇ , aY1 ⁇ ) and the display position of summary 2 ( aX2 ⁇ , aY2 ⁇ ) are shown.
  • the theme 1 above is ⁇ Children's favorite game
  • '' summary 1 is ⁇ Playing with building blocks
  • '' theme 2 is ⁇ Where to go out with children
  • summary 2 is ⁇ Children's favorite activity.'' A display example in the case of "going to the park" is shown.
  • Mode 1 In the configuration (basic example) of the conversion device 100 shown in FIG. 1, the other person's reaction determination section 140 may not be provided. In this case, the video camera 10 and the microphones and sensing devices attached to the persons 2 and 3 other than the facilitator may not be provided. However, the persons 2 and 3 may be provided with microphones 30 and 50, and the voices from the microphones 30 and 50 may be input to the character conversion section 110.
  • FIG. 5 shows a configuration in which the other person's reaction determination unit 140 is removed from the configuration of the basic example (conversion device 100 in FIG. 1).
  • the operation of the conversion device 100 of the first modification shown in FIG. 5 corresponds to the operation of the basic example except for the operation related to the other person's reaction determination unit 140.
  • the other person's reaction determining unit 140 calculates a weight indicating the other person's reaction, and the selecting unit 120 uses the weight to select a summary to be displayed from a plurality of summaries.
  • the selection unit 120 selects, for example, a summaries from among the plurality of summaries received from the character conversion unit 110, in order from the one with the earliest utterance start time. . Further, the selection unit 120 may randomly select a summaries from among the plurality of summaries received from the character conversion unit 110.
  • Modification 2 In both the basic example and modification 1, no theme may be used. In this case, for example, a summary is displayed on the coordinates (aX', aY') for each summary without displaying the theme on the display unit 190. Even if the topic is not displayed, the summaries are displayed in positions according to their mutual meanings, so summaries with similar meanings can be viewed together. In other words, the relationships between summaries can be clearly displayed.
  • FIG. 6 shows a configuration example of the conversion device 100 in Modification 2.
  • the operation configured in FIG. 6 is the operation obtained by excluding the operation related to the theme from the operation of Modification 1 (the operation excluding the operation of the other person's reaction determination unit 140 from the basic example).
  • the conversion device 100 can be realized, for example, by having a computer execute a program.
  • This computer may be a physical computer or a virtual machine on the cloud.
  • the conversion device 100 can be realized by using hardware resources such as a CPU and memory built into a computer to execute a program corresponding to the processing performed by the conversion device 100.
  • the above program can be recorded on a computer readable recording medium (such as a portable memory), and can be stored or distributed. Furthermore, it is also possible to provide the above program through a network such as the Internet or e-mail.
  • FIG. 7 is a diagram showing an example of the hardware configuration of the computer.
  • the computer in FIG. 7 includes a drive device 1000, an auxiliary storage device 1002, a memory device 1003, a CPU 1004, an interface device 1005, a display device 1006, an input device 1007, an output device 1008, etc., which are interconnected by a bus BS.
  • a program that realizes processing on the computer is provided, for example, on a recording medium 1001 such as a CD-ROM or a memory card.
  • a recording medium 1001 such as a CD-ROM or a memory card.
  • the program is installed from the recording medium 1001 to the auxiliary storage device 1002 via the drive device 1000.
  • the program does not necessarily need to be installed from the recording medium 1001, and may be downloaded from another computer via a network.
  • the auxiliary storage device 1002 stores installed programs as well as necessary files, data, and the like.
  • the memory device 1003 reads and stores the program from the auxiliary storage device 1002 when there is an instruction to start the program.
  • CPU 1004 implements functions related to conversion device 100 according to programs stored in memory device 1003.
  • the interface device 1005 is used as an interface for connecting to a network or the like.
  • a display device 1006 displays a GUI (Graphical User Interface) and the like based on a program.
  • the input device 1007 includes a keyboard, a mouse, buttons, a touch panel, or the like, and is used to input various operation instructions.
  • An output device 1008 outputs the calculation result. Note that when the conversion device 100 does not include an input unit and a display unit, the display device 1006 and the input device 1007 are not included in the computer.
  • text information can be displayed so that the relationships between a plurality of utterances can be easily read from the text information.
  • the conversion device 100 can display sentences input by the facilitator automatically arranged in a two-dimensional space, participants in the conversation can view multiple summaries with similar meanings together. can do. This has the effect of reducing the cognitive load of reading.
  • the conversion device 100 including the other person's reaction determination unit 140 can preferentially leave sentences that have a characteristic reaction, so it is possible to confirm the content of the conversation in consideration of the participants' reactions.
  • the processor converts the topic corresponding to the selected text information into coordinates corresponding to its display position, The conversion device according to supplementary note 1 or 2, wherein the topic is displayed at the coordinates obtained from the topic in the display section, and the text information is displayed at the coordinates converted from the text information selected by the selection section. .
  • the conversion device according to supplementary note 4 wherein the processor converts the reaction into a weight, and selects the text information to be displayed from the one or more weighted text information based on the weight.
  • a conversion method performed by a computer comprising: a character conversion step for converting input information into character information; a selection step of selecting character information to be displayed from one or more character information obtained in the character conversion step; A conversion method comprising: a coordinate conversion step of converting the character information selected in the selection step into coordinates corresponding to its display position.
  • Supplementary Notes 1 to 5 A non-temporary storage medium storing a program for causing a computer to function as each part of the conversion device according to any one of Supplementary Notes 1 to 5.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Machine Translation (AREA)
PCT/JP2022/028792 2022-07-26 2022-07-26 変換装置、変換方法、及びプログラム Ceased WO2024023930A1 (ja)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2024536596A JPWO2024023930A1 (https=) 2022-07-26 2022-07-26
PCT/JP2022/028792 WO2024023930A1 (ja) 2022-07-26 2022-07-26 変換装置、変換方法、及びプログラム
US18/994,282 US20260030447A1 (en) 2022-07-26 2022-07-26 Conversion apparatus, conversion method, and program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2022/028792 WO2024023930A1 (ja) 2022-07-26 2022-07-26 変換装置、変換方法、及びプログラム

Publications (1)

Publication Number Publication Date
WO2024023930A1 true WO2024023930A1 (ja) 2024-02-01

Family

ID=89705633

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/028792 Ceased WO2024023930A1 (ja) 2022-07-26 2022-07-26 変換装置、変換方法、及びプログラム

Country Status (3)

Country Link
US (1) US20260030447A1 (https=)
JP (1) JPWO2024023930A1 (https=)
WO (1) WO2024023930A1 (https=)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000105731A (ja) * 1998-09-29 2000-04-11 Fuji Xerox Co Ltd 共同作業支援装置
JP2017174172A (ja) * 2016-03-24 2017-09-28 株式会社アドバンスト・メディア 表示処理装置及び表示処理プログラム
JP2022047653A (ja) * 2020-09-14 2022-03-25 株式会社日立製作所 テキスト分類装置、テキスト分類方法及びテキスト分類プログラム

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000105731A (ja) * 1998-09-29 2000-04-11 Fuji Xerox Co Ltd 共同作業支援装置
JP2017174172A (ja) * 2016-03-24 2017-09-28 株式会社アドバンスト・メディア 表示処理装置及び表示処理プログラム
JP2022047653A (ja) * 2020-09-14 2022-03-25 株式会社日立製作所 テキスト分類装置、テキスト分類方法及びテキスト分類プログラム

Also Published As

Publication number Publication date
US20260030447A1 (en) 2026-01-29
JPWO2024023930A1 (https=) 2024-02-01

Similar Documents

Publication Publication Date Title
JP4395687B2 (ja) 情報処理装置
JP4364251B2 (ja) 対話を検出する装置、方法およびプログラム
JP7307295B1 (ja) コンテンツ提供システム、コンテンツ提供方法、及びコンテンツ提供プログラム
KR102877001B1 (ko) 인터랙션 방법 및 전자기기
JP6176041B2 (ja) 情報処理装置及びプログラム
CN105144286A (zh) 用于交互的虚拟人物对话的系统和方法
KR101567154B1 (ko) 다중 사용자 기반의 대화 처리 방법 및 이를 수행하는 장치
KR102193029B1 (ko) 디스플레이 장치 및 그의 화상 통화 수행 방법
JP2023000937A (ja) 疑似面接システム、疑似面接方法、疑似面接装置、及びプログラム
JP2020181022A (ja) 会議支援装置、会議支援システム、および会議支援プログラム
CN110992958A (zh) 内容记录方法、装置、电子设备及存储介质
JP2022126454A (ja) 表示制御プログラム、表示制御装置および表示制御方法
JP7313518B1 (ja) 評価方法、評価装置、および、評価プログラム
WO2024023930A1 (ja) 変換装置、変換方法、及びプログラム
JP7347725B1 (ja) 表示プログラム、表示方法及び表示システム
JP7775620B2 (ja) 仮想空間制御システム、その制御方法、及び、制御プログラム
JP5613102B2 (ja) 会議装置、会議方法および会議プログラム
CN111095397A (zh) 自然言语数据生成系统和方法
JP7591311B1 (ja) 動画情報検索装置、検索方法、検索プログラム、及び検索結果の利用方法
JP7625901B2 (ja) 制御装置、制御システムおよび方法
CN117876047B (zh) 评价终端的控制方法、系统、计算机设备及可读存储介质
JP7659354B1 (ja) プロフィール情報収集システム、プロフィール情報収集方法、及びプログラム
JP2021117444A (ja) 音声分析装置、音声分析方法、オンラインコミュニケーションシステム、およびコンピュータプログラム
US12556652B2 (en) Communication support system, communication support apparatus, communication support method, and storage medium
JP7671668B2 (ja) 会話管理システム及び会話管理方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22953027

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2024536596

Country of ref document: JP

WWE Wipo information: entry into national phase

Ref document number: 18994282

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22953027

Country of ref document: EP

Kind code of ref document: A1

WWP Wipo information: published in national office

Ref document number: 18994282

Country of ref document: US